Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1778 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4992. Min Act: -0.0001

Data Index: 633044 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.5041. Min Act: -0.0001

Data Index: 1293171 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4615. Min Act: -0.0001

Data Index: 996070 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1343158 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4637. Min Act: -0.0001

Data Index: 305417 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4180. Min Act: -0.0001

Data Index: 688861 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4315. Min Act: -0.0001

Data Index: 240936 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.3872. Min Act: -0.0001

Data Index: 1015585 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1168820 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4071. Min Act: -0.0001

Data Index: 880400 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4080. Min Act: -0.0001

Data Index: 1344326 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4038. Min Act: -0.0001

Data Index: 1080500 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.3915. Min Act: -0.0001

Data Index: 93474 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4144. Min Act: -0.0001

Data Index: 978090 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1283147 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4527. Min Act: -0.0001

Data Index: 843136 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.4884. Min Act: -0.0001

Data Index: 579329 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.3803. Min Act: -0.0001

Data Index: 655458 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1086478 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.5041. Min Range: -0.5041

Max Act: 0.3924. Min Act: -0.0001

Data Index: 223016 (C4 (Web Text))

Max Activating Token Index: 744